Leveraging Big Data Networks and Reality Mining for HR Marketing and Labor Market: Insight for Uzbekistan
Annotatsiya
Due to the huge potential in big data-driven labor analytics, which is helpful for human resource marketing, talent allocation, and labor market forecasting, the integrated network-based framework was proposed and was widely used in employment dynamics research. The objective of this study is to evaluate human resource marketing performance (data-driven recruitment, workforce segmentation, skills matching), and labor market adaptability (regional demand shifts, sectoral mobility) using AHP-TOPSIS hybrid methods for enhanced multi-criteria assessment of labor flows in the human resource ecosystem and the employment network in Uzbekistan. In order to understand the behavioral data of workforce interactions, this research analyzes the network topology data of labor participants in different sectors of the economy based on conceptual mapping and multi-layer network analysis and makes recommendations on the adaptive data in urban, peri-urban, and rural clusters of employment structures. This captures the development status of HR marketing systems and the determinants affecting the mobility of labor resources and analyzes them under the AHP prioritization and TOPSIS analysis method. A weighted synthesis of each criterion is used as the benchmark information in addition to consistency ratios for the ranking and decision-making methods. Results indicate that among the evaluated approaches, the AHP-TOPSIS integration is found to be the best decision support mechanism for estimating labor market distribution in both the short and long term with the lowest prediction error between the observed and estimated allocations. Thus, this framework demonstrates that the use of reality mining indicators as an auxiliary variable in addition to big data network metrics in the conceptual mapping model can significantly enhance the estimation of human capital dynamics over a multi-scenario horizon.